python lightgbm中使用“early_stopping_rounds”和“verbose_eval”出现 UserWarning

问题：

调用lightgbm库，设置了早停轮次“early_stopping_rounds”参数和打印log间隔“verbose_eval”参数后出现UserWarning

示例代码如下：

import lightgbm

cv_results = lightgbm.cv(
                    params,
                    lgb_train,
                    seed=1,
                    nfold=5,
                    metrics='auc',
                    ###
                    early_stopping_rounds=30, 
                    verbose_eval=True 
                    ###
                    )        

两个UserWarning如下：

UserWarning: 'early_stopping_rounds' argument is deprecated and will be removed in a future release of LightGBM. Pass 'early_stopping()' callback via 'callbacks' argument instead.

UserWarning: 'verbose_eval' argument is deprecated and will be removed in a future release of LightGBM. Pass 'log_evaluation()' callback via 'callbacks' argument instead.

原因：

'early_stopping_rounds' argument is deprecated and will be removed in a future release of LightGBM. Pass 'early_stopping()' callback via 'callbacks' argument instead. 的意思是参数'early_stopping_rounds' 已被弃用，将在LightGBM的未来版本中删除。改为通过“callbacks”参数传入“early_stopping（）”。

由于LightGBM库在更新之后将老版本的函数进行了改动，导致需要传入的参数或传入参数的方式发生了改变。

解决方法：

将代码做如下修改

import lightgbm

###
from lightgbm import log_evaluation, early_stopping
callbacks = [log_evaluation(period=100), early_stopping(stopping_rounds=30)]
###

cv_results = lightgbm.cv(
                    params,
                    lgb_train,
                    seed=1,
                    nfold=5,
                    metrics='auc',
                    ###
                    callbacks=callbacks
                    ###
                    )

首先

from lightgbm import log_evaluation, early_stopping

之后用

callbacks = [log_evaluation(period=100), early_stopping(stopping_rounds=30)]

替换之前的'verbose_eval'以及'early_stopping_rounds'即可:)

其中period=100指每迭代100次打印一次log；stopping_rounds=30指如果验证集的误差在30次迭代内没有降低，则停止迭代。